检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Jingwei Wang, Chuansheng Huang, Jiayan Fan, Haoyi Grau, Antoni Zhang, Fuquan The College of Computer and Big Data Fuzhou University Fuzhou China The Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain The New Engineering Industry College Putian University Putian China School of Computer and Artificial Intelligence Zhengzhou University China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Control Engineering Minjiang University Fuzhou China Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu China Fuzhou Technology Innovation Center of Intelligent Manufacturing information System Minjiang University Fuzhou China Fujian Polytechnic Normal University Fujian Province University Fuzhou China

Driver drowsiness electroencephalography (EEG) signal monitoring can timely alert drivers of their drowsiness status, thereby reducing the probability of traffic accidents. Graph convolutional networks (GCNs) have shown significant advancements in processing the non-stationary, time-varying, and non-Euclidean nature of EEG signals. However, the existing single-channel EEG adjacency graph construction process lacks interpretability, which hinders the ability of GCNs to effectively extract adjacency graph features, thus affecting the performance of drowsiness monitoring. To address this issue, we propose an edge-end lightweight dual graph convolutional network (LDGCN). Specifically, we are the first to incorporate neurophysiological knowledge to design a Baseline Drowsiness Status Adjacency Graph (BDSAG), which characterizes driver drowsiness status. Additionally, to express more features within limited EEG data, we introduce the Augmented Graph-level Module (AGM). This module captures global and local information at the graph level, ensuring that BDSAG features remain intact while enhancing effective feature expression capability. Furthermore, to deploy our method on the fourth-generation Raspberry Pi, we utilize Adaptive Pruning Optimization (APO) on both channels and neurons, reducing inference latency by almost half. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization compared to existing state-of-the-art algorithms. All our source code can be found at https://***/BryantDom/Driver-Drowsiness-Monitoring. Copyright © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Electrical Engineering

引用

Lecture Notes in Electrical Engineering 2024年 1114 LNEE卷 v页

作者： Lin, Jerry Chun-Wei Shieh, Chin-Shiuh Horng, Mong-Fong Chu, Shu-Chuan Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and IT Devices Silesian University of Technology Gliwice Poland

来源：评论

学校读者我要写书评

暂无评论

Texture Analysis of Breast US Images Using Morphological Transforms, Hausdorff Dimension and Bagging Ensemble Method

Texture Analysis of Breast US Images Using Morphological Tra...

引用

Mediterranean Conference on control and Automation (MED)

作者： Gigi Tăbăcaru Simona Moldovanu Marian Barbu Department of Automatic Control and Electrical Engineering Faculty of Automation Computers Electrical Engineering and Electronics “Dunarea de Jos” University of Galati Romania Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics “Dunarea de Jos” University of Galati The Modelling & Simulation Laboratory Dunarea de Jos University of Galati Galati Romania

ISBN: (数字)9798350395440

ISBN: (纸本)9798350395457

In this work, an attempt is made for the first time to use the measurement pattern generated by morphological transformation quantified by Hausdorff fractal dimension (HFD) and classified with ensemble learning based on bagging. The proposed work uses three morphological transformations for image preprocessing: hit-and-miss transform (HMT), white (WHT), and black top-hat (BHT). The pattern texture of US breast images is described by extracting the HFD from the regions of interest (ROI) after the ultrasound (US) images have been preprocessed. The main objective of this study was achieved by comparatively analyzing the classification performance of features using the Random Forest (RF), Extra Trees (ET) classifier, and bagging ensemble method based on XGBoot classifier. In presented study, the XGBoost classifier and BHT image processing method give an accuracy of 89.8% in a binary classification, benign versus malignant breast cancer.

关键词： Ultrasonic imaging Transforms Feature extraction Time measurement Fractals Ensemble learning Image preprocessing

来源：评论

学校读者我要写书评

暂无评论

Comparing concepts of quantum and classical neural network models for image classification task

arXiv

引用

arXiv 2021年

作者： Potempa, Rafal Porebski, Sebastian Department of Cybernetics Nanotechnology and Data Processing Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

While quantum architectures are still under development, when available, they will only be able to process quantum data when machine learning algorithms can only process numerical data. Therefore, in the issues of classification or regression, it is necessary to simulate and study quantum systems that will transfer the numerical input data to a quantum form and enable quantum computers to use the available methods of machine learning. This material includes the results of experiments on training and performance of a hybrid quantum-classical neural network developed for the problem of classification of handwritten digits from the MNIST data set. The comparative results of two models: classical and quantum neural networks of a similar number of training parameters, indicate that the quantum network, although its simulation is time-consuming, overcomes the classical network (it has better convergence and achieves higher training and testing accuracy). © 2021, CC BY.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach

arXiv

引用

arXiv 2024年

作者： Zhao, Hongyu Tang, Zezhi Li, Zhenhong Dong, Yi Si, Yuancheng Lu, Mingyang Panoutsos, George The Department of Physics Imperial College London United Kingdom The Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS1 3JD United Kingdom The Department of Electrical and Electronic Engineering University of Manchester Manchester United Kingdom The Department of Electronics and Computer Science University of Southampton Southampton United Kingdom The Department of Economics Fudan University Shanghai200433 China Iowa State University AmesIA50011 United States

The optimisation of crop harvesting processes for commonly cultivated crops is of great importance in the aim of agricultural industrialisation. Nowadays, the utilisation of machine vision has enabled the automated identification of crops, leading to the enhancement of harvesting efficiency, but challenges still exist. This study presents a new framework that combines two separate architectures of convolutional neural networks (CNNs) in order to simultaneously accomplish the tasks of crop detection and harvesting (robotic manipulation) inside a simulated environment. Crop images in the simulated environment are subjected to random rotations, cropping, brightness, and contrast adjustments to create augmented images for dataset generation. The you only look once algorithmic framework is employed with traditional rectangular bounding boxes (R-Bbox) for crop localization. The proposed method subsequently utilises the acquired image data via a visual geometry group model in order to reveal the grasping positions for the robotic manipulation. Copyright © 2024, The Authors. All rights reserved.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2021年

作者： Grussler, Christian Rantzer, Anders Department of Electrical Engineering and Computer Sciences UC Berkeley BerkeleyCA United States Department of Automatic Control Lund University Lund Sweden

We address the issue of establishing standard forms for nonnegative and Metzler matrices by considering their similarity to nonnegative and Metzler Hessenberg matrices. It is shown that for dimensions n ≥ 3, there always exists a subset of nonnegative matrices that are not similar to a nonnegative Hessenberg form, which in case of n = 3 also provides a complete characterization of all such matrices. For Metzler matrices, we further establish that they are similar to Metzler Hessenberg matrices if n ≤ 4. In particular, this provides the first standard form for controllable third order continuous-time positive systems via a positive controller-Hessenberg form. Finally, we present an example which illustrates why this result is not easily transferred to discrete-time positive systems. While many of our supplementary results are proven in general, it remains an open question if Metzler matrices of dimensions n ≥ 5 remain similar to Metzler Hessenberg *** Codes 15A21, 15B48, 93C05 Copyright © 2021, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Enabling IoT Continuous Connectivity in Smart Spaces

Enabling IoT Continuous Connectivity in Smart Spaces

引用

International Symposium on Parallel and Distributed Computing

作者： Andreas Andreou Constandinos X. Mavromoustakis Jordi Mongay Batalla Ciprian Dobre Evangelos Markakis George Mastorakis Departement of Computer Science University of Nicosia and University of Nicosia Research Foundation Nicosia Cyprus Warsaw University of Technology Warsaw Poland Automatic Control and Computers University Politehnica of Bucharest National Institute for Research and Development in Informatics Bucharest Romania Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece Department of Management Science and Technology Hellenic Mediterranean University Agios Nikolaos Greece

Smart spaces are a rapidly emerging concept in technology. They result from the convergence of various novel technologies, such as the Internet of Things, Machine Learning and Artificial Intelligence, which allow for greater levels of automation and control within physical environments. The devices which are connected to the IoT network are equipped with sensors to acquire and exchange data. As a result, the IoT has transformed how we live, work, and play. However, the deployment in smart spaces is not always the best due to the issues arising from network node positioning. Therefore, we are investigating solutions to this problem with a novel approach which utilises Voronoi diagrams in conjunction with the algorithmic genetic technique. First, the initial positions of the IoT nodes will be determined by simulating a homogeneous Poisson point process in the smart space environment. Then, after dividing the area into the Voronoi cells, the genetic algorithm will optimise the position towards achieving full network coverage within the smart space. Experimental results prove the 100% network coverage within the specified area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Power-balancing dual-port grid-forming power converter control for renewable integration and hybrid AC/DC power systems

arXiv

引用

arXiv 2021年

作者： Subotić, Irina Groß, Dominic Automatic Control Laboratory ETH Zürich Switzerland Department of Electrical and Computer Engineering The University of Wisconsin-Madison United States

In this work, we investigate grid-forming (GFM) control for dc/ac power converters in emerging power systems that contain ac and dc networks, renewable generation, and conventional generation. We propose a change in control paradigm to a universal dual-port GFM control strategy that simultaneously forms the converter ac and dc voltage (i.e., dual-port GFM), unifies standard functions of grid-following (GFL) and GFM (e.g., primary frequency control, maximum power point tracking) in a single universal controller, and is backwards compatible with conventional machine-based generation. Notably, in contrast to state-of-the-art control architectures that use a mix of grid-forming and grid-following control, dual-port GFM control can be used independently of the converter power source or network configuration. Our main contribution are stability conditions that cover emerging hybrid ac/dc networks as well as machines and converters with and without controlled power source, that only require partial knowledge of the network topology. Finally, a detailed case study is used to illustrate and validate the results. Copyright © 2021, The Authors. All rights reserved.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling Under Data Governance

SSRN

引用

SSRN 2023年

作者： Qin, Zhaoming Dong, Nanqing Liu, Di Cao, Junwei Automatic Control Laboratory EPFL Lausanne1015 Switzerland Department of Computer Science University of Oxford OxfordOX1 3QD United Kingdom Department of Electrical Engineering Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. In a simplified scenario, centralized training, the most common paradigm for MARL, precludes large-scale deployment of MARL in communication-constrained cloud-edge environments. As a remedy, distributed training shows unparalleled advantages in real-life application scenarios compared with its centralized counterpart. However, distributed training still faces the challenge of system scalability, e.g., the high communication burden during coordinating individual agents, and needs to comply with data governance in terms of privacy. In this work, we propose a novel MARL solution to address these two practical issues. The proposed solution is based on actor-critic methods, where the global critic is a learned function of individual critics computed solely based on local observations of residences. In this way, the private data of residences is preserved completely and the communication cost is reduced significantly. The simulation experiments demonstrate that the proposed framework can achieve comparable performance to the state-of-the-art actor-critic framework without data governance and communication constraints. © 2023, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A novel pipeline employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy

引用

computers in Biology and Medicine 2024年 181卷 109052-109052页

作者： Mamalakis, Michail Macfarlane, Sarah C. Notley, Scott V. Gad, Annica K.B. Panoutsos, George School of Electrical and Electronic Engineering University of Sheffield Sheffield United Kingdom Insigneo Institute for in-silico Medicine University of Sheffield Sheffield United Kingdom Department of Infection Immunity and Cardiovascular Disease Department of Computer science Sheffield United Kingdom Department of Psychiatry Cambridge University Cambridge United Kingdom Department of Oncology and Metabolism The Medical School University of Sheffield Sheffield United Kingdom Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom Madeira Chemistry Research Centre University of Madeira Funchal Portugal Department of Oncology-Pathology Karolinska Institutet Stockholm Sweden

Metastasis driven by cancer cell migration is the leading cause of cancer-related deaths. It involves significant changes in the organization of the cytoskeleton, which includes the actin microfilaments and the vimentin intermediate filaments. Understanding how these filament change cells from normal to invasive offers insights that can be used to improve cancer diagnosis and therapy. We have developed a computational, transparent, large-scale and imaging-based pipeline, that can distinguish between normal human cells and their isogenically matched, oncogenically transformed, invasive and metastasizing counterparts, based on the spatial organization of actin and vimentin filaments in the cell cytoplasm. Due to the intricacy of these subcellular structures, manual annotation is not trivial to automate. We used established deep learning methods and our new multi-attention channel architecture. To ensure a high level of interpretability of the network, which is crucial for the application area, we developed an interpretable global explainable approach correlating the weighted geometric mean of the total cell images and their local GradCam scores. The methods offer detailed, objective and measurable understanding of how different components of the cytoskeleton contribute to metastasis, insights that can be used for future development of novel diagnostic tools, such as a nanometer level, vimentin filament-based biomarker for digital pathology, and for new treatments that significantly can increase patient survival. © 2024

关键词： Fluorescence microscopy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：